diff options
| author | Justsoos <justso@gmail.com> | 2017-02-01 21:30:01 +0800 |
|---|---|---|
| committer | Sergey M․ <dstftw@gmail.com> | 2017-02-03 03:26:41 +0700 |
| commit | 33da98f4933ddc54c944bae985cfcc7b53563208 (patch) | |
| tree | 8dda2a6c957bea82d303e7c278e74c248e65e590 | |
| parent | 4195096ea8da8237a63e1ba3876dc8856b8605c6 (diff) | |
[douyutv] Improve room id regex
http://www.douyu.com/t/lpl source get extra '\' with "room_id\" (from js coding)
| -rw-r--r-- | youtube_dl/extractor/douyutv.py | 8 |
1 files changed, 6 insertions, 2 deletions
diff --git a/youtube_dl/extractor/douyutv.py b/youtube_dl/extractor/douyutv.py index 2f3c5113e..911594413 100644 --- a/youtube_dl/extractor/douyutv.py +++ b/youtube_dl/extractor/douyutv.py @@ -18,7 +18,7 @@ from ..utils import ( class DouyuTVIE(InfoExtractor): IE_DESC = '斗鱼' - _VALID_URL = r'https?://(?:www\.)?douyu(?:tv)?\.com/(?P<id>[A-Za-z0-9]+)' + _VALID_URL = r'https?://(?:www\.)?douyu(?:tv)?\.com/(?:[^/]+/)*(?P<id>[A-Za-z0-9]+)' _TESTS = [{ 'url': 'http://www.douyutv.com/iseven', 'info_dict': { @@ -68,6 +68,10 @@ class DouyuTVIE(InfoExtractor): }, { 'url': 'http://www.douyu.com/xiaocang', 'only_matching': True, + }, { + # \"room_id\" + 'url': 'http://www.douyu.com/t/lpl', + 'only_matching': True, }] # Decompile core.swf in webpage by ffdec "Search SWFs in memory". core.swf @@ -82,7 +86,7 @@ class DouyuTVIE(InfoExtractor): else: page = self._download_webpage(url, video_id) room_id = self._html_search_regex( - r'"room_id"\s*:\s*(\d+),', page, 'room id') + r'"room_id\\?"\s*:\s*(\d+),', page, 'room id') room = self._download_json( 'http://m.douyu.com/html5/live?roomId=%s' % room_id, video_id, |